Research map / Label-efficient and robust learning / Domain adaptation and generalization
Joint distribution optimal transportation for domain adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply JDOT instead of the strongest reported baseline | Caltech-Office classification · Caltech-Office mean | accuracy: 86.95 -> 89.04 | Helped |
| Apply JDOT (Hinge) instead of DANN | Amazon review classification · Amazon review mean | accuracy: 0.763 -> 0.787 | Helped |
| Use Hinge loss instead of mse (ablation) | JDOT on Amazon reviews · Amazon review mean | accuracy: 0.783 -> 0.787 | Helped |
| Apply JDOT instead of DIP-CC | Wifi localization · t1 → t2 | accuracy: 91.30 ± 3.24 -> 93.03 ± 1.24 | Helped |
| Apply JDOT instead of SurK | Wifi localization · t1 → t3 | accuracy: 94.97±1.29 -> 90.06 ± 2.01 | Hurt |
| Apply JDOT instead of CTC-TIP | Wifi localization · t2 → t3 | accuracy: 89.52 $\pm$ 1.14 -> 86.76 ± 1.72 | Hurt |
| Apply JDOT instead of the strongest baseline | Wifi localization across devices · hallway1 | accuracy: 86.98 $\pm$ 2.02 -> 98.83$\pm$0.58 | Helped |
| Apply JDOT instead of the strongest baseline | Wifi localization across devices · hallway2 | accuracy: 87.94 $\pm$ 2.07 -> 98.45$\pm$0.67 | Helped |
| Apply JDOT instead of CTC | Wifi localization across devices · hallway3 | accuracy: 82.02$\pm$ 2.34 -> 99.27$\pm$0.41 | Helped |
| Balance label discrepancy with feature-space distance instead of relying mostly on label cost (ablation) | JDOT with RBF kernel on the toy classification example · Toy classification | accuracy | Helped |
| Use feature-space distance alone rather than the joint feature-and-label cost (ablation) | JDOT with RBF kernel on the toy classification example · Toy classification | accuracy | Mixed |
Closest papers by meaning
- Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation (CVPR 2020 · similarity 0.89)
- Prototypical Partial Optimal Transport for Universal Domain Adaptation (AAAI 2023 · similarity 0.89)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.88)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.87)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.87)
- On $f$-Divergence Principled Domain Adaptation: An Improved Framework (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.